llama.cpp/tests/test-backend-ops.cpp at 2016bf2b3bca10e49e06a00586a8a2fde9f6cc32

mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-08-04 09:00:48 -05:00

Files

Reese Levine e8c54893f2 ggml-webgpu: FlashAttention refactor + standardize quantization support (#23834 )

* Start work on flash_attn refactor

* Refactor

* Split k/v quantization

* Refactor and abstract quantization logic for flash_attn and mul_mat

* Add quantization support to tile path

* formatting

* Move to functions, add a check

2026-06-04 08:05:04 +03:00

397 KiB

Raw Blame History

View Raw

397 KiB Raw Blame History

397 KiB

Raw Blame History